Timothy Baldwin

Mohamed bin Zayed University of Artificial Intelligence — AE

Computer Science · Physical Sciences

38h-index6.7kcitations223works1.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(98), Natural Language Processing Techniques(59), Biomedical Text Mining and Ontologies(38), Advanced Text Analysis Techniques(25), Speech and dialogue systems(15)

Publications223 total

Control Illusion: The Failure of Instruction Hierarchies in Large Language Models
Underline Science Inc.·2026Open Access
Training and Evaluating with Human Label Variation: An Empirical Study
Computational Linguistics·2025Open Access
Learning Robust Negation Text Representations
arXiv (Cornell University)·2025Open Access
Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs
arXiv (Cornell University)·2025Open Access
Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
arXiv (Cornell University)·2025Open Access
Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts
2025· 1 citedOpen Access
Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models
2025Open Access
Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
2025· 1 citedOpen Access
A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
2025· 1 citedOpen Access
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
2025Open Access
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
arXiv (Cornell University)·2024Open Access
Zero‐ and few‐shot prompting of generative large language models provides weak assessment of risk of bias in clinical trials
Research Synthesis Methods·2024· 15 citedOpen Access
An Ethical Dataset from Real-World Interactions Between Users and Large Language Models
2024
Predicting Publication of Clinical Trials Using Structured and Unstructured Data
Zenodo (CERN European Organization for Nuclear Research)·2024Open Access
Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
arXiv (Cornell University)·2024Open Access
Revisiting subword tokenization: A case study on affixal negation in large language models
arXiv (Cornell University)·2024· 1 citedOpen Access
Eagle: Ethical Dataset Given from Real Interactions
arXiv (Cornell University)·2024Open Access
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
2024· 3 cited
Revisiting subword tokenization: A case study on affixal negation in large language models
2024· 1 citedOpen Access
page 1 of 12Next →

Frequent Co-authors

Jey Han Lau(12), Karin Verspoor(11), David Newman(8), Doris Hoogeveen(4), Paul Cook(4), James R. Gilkerson(4), Trevor Cohn(4), Sarvnaz Karimi(3), Diana McCarthy(3), Brian Hur(3), Laura Y. Hardefeldt(3), Yuh Nung Jan(2), Lily Yeh Jan(2), Karl Grieser(2), Bo Han(2), Tristan McCaughey(2), Paul G. Sanfilippo(2), George E.C. Gooden(2), David Budden(2), Eva Fenwick(2)